Exploring how to model forest structure and quantify ecosystem services using Python and Earth observation data (GEDI, Sentinel-1, Sentinel-2, SRTM) with data preprocessing, machine learning (Random Forest), and SHAP interpretation to understand variable importance. Estimating canopy height and aboveground biomass and mapping forest ecosystem services for monitoring and climate research. Case study combining GEDI, Sentinel, and SRTM data.
talk-data.com
L
Speaker
Laya Zeinali
1
talks
PhD candidate
Tarbiat Modares University
PhD candidate focusing on forest remote sensing and assessment of forest ecosystem services; applying machine learning to analyze multi-sensor remote sensing data, including GEDI, LiDAR, radar, and optical imagery, for estimating forest carbon stocks, biomass, and ecosystem services.
Bio from: [Online] Analyzing Geospatial Forest Data with Geopandas and Rasterio
Filter by Event / Source
Talks & appearances
1 activities · Newest first